Geometric Representation Learning for Document Image Rectification
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Hao Feng, Wengang Zhou, Jiajun Deng, Yuechen Wang, Houqiang Li
In document image rectification, there exist rich geometric constraints between the distorted image and the ground truth one. However, such geometric constraints are largely ignored in existing advanced solutions, which limits the rectification performance. To this end, we present DocGeoNet for document image rectification by introducing explicit geometric representation. Technically, two typical attributes of the document image are involved in the proposed geometric representation learning, i.e., 3D shape and textlines. Our motivation arises from the insight that 3D shape provides global unwarping cues for rectifying a distorted document image while overlooking the local structure. On the other hand, textlines complementarily provide explicit geometric constraints for local patterns. The learned geometric representation effectively bridges the distorted image and the ground truth one. Extensive experiments show the effectiveness of our framework and demonstrate the superiority of our DocGeoNet over state-of-the-art methods on both the DocUNet Benchmark dataset and our proposed DIR300 test set. The code is available at https://github.com/fh2019ustc/DocGeoNet.
University of Science and Technology of China（中国科学技术大学）；Zhangjiang Laboratory（张江实验室）；The University of Adelaide（阿德莱德大学）；Australian Institute for Machine Learning（澳大利亚机器学习研究所）
Unfolder: Fast localization and image rectification of a document with a crease from folding in half
Smart Engines Service LLC（Smart Engines服务有限责任公司）；Institute for Information Transmission Problems of RAS (Kharkevich Institute)（俄罗斯科学院信息传输问题研究所（哈尔凯维奇研究所））；Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences（俄罗斯科学院计算机科学与控制联邦研究中心）
National ICT Australia (NICTA)（澳大利亚国家信息与通信技术研究院（NICTA））；Australian National University（澳大利亚国立大学）；Osaka University（大阪大学）；Microsoft Research Redmond（微软雷德蒙德研究院）；Microsoft, Japan（微软（日本））；Microsoft Research Asia（微软亚洲研究院）
Marior: Margin Removal and Iterative Content Rectification for Document Dewarping in the Wild
South China University of Technology（华南理工大学）；Peng Cheng Laboratory（鹏城实验室）；Pazhou Laboratory (Huangpu)（琶洲实验室（黄埔））；IntSig Information Co. Ltd（合合信息科技股份有限公司）
Cascaded Robust Rectification for Arbitrary Document Images
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家级实验室）；National Engineering Research Center for Visual Information and Applications（视觉信息与应用国家工程研究中心）；Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）；Xi’an Jiaotong University（西安交通大学）；The University of Tokyo（东京大学）
Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification
South China University of Technology（南方科技大学）；State Key Laboratory of Subtropical Building Science（亚热带建筑科学国家重点实验室）；Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information（广东省计算智能与网络信息重点实验室）；Ministry of Education Key Laboratory of Big Data and Intelligent Robot（教育部大数据与智能机器人重点实验室）；Singapore Management University（新加坡国立大学）
Towards Human-Like Machine Comprehension: Few-Shot Relational Learning in Visually-Rich Documents
School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）；Graduate School of Informatics, Kyoto University（京都大学信息学研究科）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程系）
Fast Projective Image Rectification for Planar Objects with Manhattan Structure
Federal Research Center “Computer Science and Control” of Russian Academy of Sciences（俄罗斯科学院“计算机科学与控制”联邦研究中心）；Moscow Institute of Physics and Technology (State University)（莫斯科物理技术学院（国立大学））；The Institute for Information Transmission Problems of Russian Academy of Sciences（俄罗斯科学院信息传输问题研究所）；Smart Engines Service LLC（Smart Engines服务有限责任公司）
A Deep Single Image Rectification Approach for Pan-Tilt-Zoom Cameras
School of Computer Science, Hubei University of Technology（湖北工业大学计算机学院）；Hubei Key Laboratory of Green Intelligent Computing Power Network（湖北绿色智能算力网络重点实验室）；School of Surveying and Mapping, Wuhan University（武汉大学测绘学院）；Wuhan Tianjihang Information Technology Co., Ltd.（武汉天起航信息技术有限公司）
Advanced Hough-based method for on-device document localization
Moscow Institute of Physics and Technology (National Research University)（莫斯科物理技术学院（国家研究型大学））；FRC CSC RAS（俄罗斯科学院计算机科学控制问题研究中心）；Moscow State University（莫斯科国立大学）；Institute for Information Transmission Problems of the RAS (Kharkevich Institute)（俄罗斯科学院信息传输问题研究所（哈尔克维奇研究所））；LLC "Smart Engines Service"（智能引擎服务有限责任公司）
Robust Scene Text Recognition with Automatic Rectification
Huazhong University of Science and Technology（华中科技大学）
在自然图像中识别文本是一项具有挑战性的任务，有许多未解决的问题。与文档中的文字不同，自然图像中的文字通常具有不规则的形状，这是由透视变形，弯曲的字符放置等引起的。我们提出了RARE（Robust text recognizer with Automatic Rectification），一种对不规则文本具有鲁棒性的识别模型。RARE是一种特殊设计的深度神经网络，由空间Transformer网络（SPIRE）和序列识别网络（SRN）组成。在测试中，首先通过预测的薄板样条（TPS）变换将图像校正为更“可读”的图像，以供随后的SRN使用，SRN通过序列识别方法识别文本。我们表明，该模型能够识别几种类型的不规则文本，包括透视文本和弯曲的文本。RARE是端到端可训练的，只需要图像和相关的文本标签，便于在实际系统中训练和部署模型。国家的最先进的或高度竞争力的性能达到几个基准很好地证明了所提出的模型的有效性。
Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation of Chinese Academy of Sciences（中国科学院自动化研究所）；CAS Center for Excellence of Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Liangzhu Laboratory and WeDoctor Cloud（良渚实验室和微医云）；Shanghai Innovation Institute（上海创新研究院）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；State Key Laboratory of Transvascular Implantation Devices and TIDRI（经血管植入器械全国重点实验室和TIDRI）；Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence（浙江省医学影像人工智能重点实验室）
Spectral Rectification for Parameter-Efficient Adaptation of Foundation Models in Colonoscopy Depth Estimation
Department of Biomedical Engineering, National University of Singapore, Singapore（新加坡国立大学生物医学工程系）；Department of Radiotherapy, The First Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China（西安交通大学第一附属医院放疗科）
D$^2$Turb: Depth-Aware Simulation and Decoupled Learning for Single-Frame Atmospheric Turbulence Mitigation
University of Electronic Science and Technology of China（电子科技大学）；Beijing Institute of Space Mechanics and Electricity（北京空间机械与电子研究所）；School of Physics, Northwest University Xi'an（西安西北大学物理学院）
DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Institute of Information Engineering, Chinese Academy of Sciences；VCIP \& TMCC \& DISSec, College of Computer Science \& College of Cryptology；Cyber Science, Nankai University；School of Cyber Security, University of Chinese Academy of Sciences
